Generalized Likelihood Ratio Statistics and Uncertainty Adjustments in Efficient Adaptive Design of Clinical Trials

摘要

A new approach to adaptive design of clinical trials is proposed in a generalmultiparameter exponential family setting, based on generalized likelihoodratio statistics and optimal sequential testing theory. These designs are easyto implement, maintain the prescribed Type I error probability, and areasymptotically efficient. Practical issues involved in clinical trials allowingmid-course adaptation and the large literature on this subject are discussed,and comparisons between the proposed and existing designs are presented inextensive simulation studies of their finite-sample performance, measured interms of the expected sample size and power functions.